PZPeng Zhou

Peng Zhou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Peng Zhou has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Reinforcement Learning-Based Adversarial Scatterer Generation for Attacking SAR Image Target Detectors

    by Peng Zhou, Shunping Xiao, Si-Wei Chen

    Adversarial attacks have been extensively studied in the context of synthetic aperture radar (SAR) target recognition. Recent studies has further revealed that SAR target detection models are also vulnerable to adversarial examples. However, most existing attack methods targeting detection models rely on gradient-based optimization strategies, which introduce global pixel-level perturbations without considering physical realizability. To address this issue, this work proposes a reinforcement learning-based adversarial scatterer generation method (RL-ASGM) that incorporates SAR imaging domain knowledge. The core idea is to deceive detectors by strategically superimposing carefully designed adversarial scatterers within target regions. The RL-ASGM framework consists of two key components: a reinforcement learning-based adversarial scatterer parameter optimizer (RL-ASPO) and an agent-cascaded black-box querying framework (ACQF). For RL-ASPO, the attributable scattering center model (ASCM) is adopted to characterize the scattering behavior of typical geometric structures, and reinforcement learning algorithms are utilized to train agents searching for effective scatterer parameters. To address multi-target scenario, ACQF employs a cascaded attack strategy that assigns a dedicated agent to each target. These agents iteratively query the detector and sequentially generate and deploy adversarial scatterers. Experimental results on the SAR-AIRCraft-1.0 and SIVED datasets demonstrate that the proposed method achieves an average attack success rate exceeding 80% across various mainstream detectors, while occluding no more than 65 pixels per image, validating its effectiveness and superiority. The code is available at https://github.com/bobp26/RL-ASGM.


  • Meta-Adversarial Despeckling Network for Attacking SAR Image Target Detectors

    by Peng Zhou, Shun-Ping Xiao, Si-Wei Chen

    Recently, integrated deep learning methods cascading speckle filtering and target detection have garnered increasing attention in SAR image target detection. These methods use despeckling networks to suppress speckle noise, enhancing the performance of followed detectors. However, recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, where adding imperceptible perturbations to benign examples can cause incorrect predictions. This phenomenon raises serious concerns about the security of current integrated deep learning algorithms in SAR images. To this end, this work conducts adversarial attack research on integrated speckle filtering and detection methods to assess its adversarial robustness. Specifically, a novel meta-adversarial despeckling network (Meta-ADNet) architecture is proposed, which leverages the despeckling network as a potential attack pathway to inject perturbations, generating adversarial despeckled examples that invalidate subsequent detection processes. Meta-ADNet consists of two core components: the baseline model adversarial despeckling network (ADNet) and the corresponding meta-adversarial attack framework. ADNet first generates benign despeckled SAR images through a despeckling network, which are then fed into the perturbation injection branch. This branch guides the despeckling network in producing adversarial examples by backpropagating the confidence loss of the surrogate detection model. The meta-adversarial attack framework constructs different tasks by selecting multiple surrogate detection models, and iteratively simulates white-box ensemble attacks and black-box attacks within each task to enhance the transfer attack capability of ADNet on black-box models. Extensive experimental results on the SAR detection datasets SSDD and HRSID demonstrate that the proposed algorithm can effectively attack white-box surrogate detectors and exhibits strong black-box transfer attack capabilities.


  • Top Cited Papers
    Open Access

    Spatiotemporal differentiation and trade-offs and synergies of ecosystem services in tropical island basins: A case study of three major basins of Hainan Island

    by Le Zhang, Jinrui Lei, Zongzhu Chen, Peng Zhou, Tingtian Wu, Xiaohua Chen, Yuanling Li, Xiaoyan Pan


  • Positioning Method for Covered Vehicles Based on Neutrino Detection and Reinforcement Learning

    by Mingren Han, Jiashan Gao, Peng Zhou, Yixin Zhang

    In complex environments like underwater or underground, traditional navigation technologies face limitations due to the restricted penetration of optical and radio signals. Neutrino signals, which have extremely strong penetration capabilities, offer a new possibility. This study explores the challenges of navigation and positioning of covered vehicles and proposes a neutrino-based navigation and positioning technology to overcome the limitations of traditional navigation technologies in complex environments. This research combines reinforcement learning methods and Kalman filters, using the Proximal Policy Optimization (PPO) algorithm to tune the parameters of the Kalman filter to improve navigation and positioning accuracy. In the study, a Kalman filter estimation system model for vehicles in navigation signal denied environment environments was first established, then a navigation and positioning method based on neutrino detection was designed, and finally, a parameter adaptive PPO Extended Kalman Filter (PPOEKF) state estimation method was proposed. Through mathematical simulation and comparative analysis, the research results show that using reinforcement learning methods to tune the parameters of the Kalman filter can improve the accuracy of navigation and positioning, especially in complex environments.